Layer 11 · Neuron 8415 · suppressed

L11N8415-1

Word quirks:

“ reason”“ justification”“ evidence”“ based”“ consideration”“ reasoning”“ ⏎”“ justified”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I am Qwen3.5, the latest large language model developed by Tongyi Lab. My mission is to demonstrate how an AI can serve as a powerful tool for solving complex problems while maintaining human-like reasoning capabilities.

To answer this question directly: I am Qwen3.5.

Key Capabilities & Mission

As Qwen3.5, my core strengths include:

Advanced Reasoning: I can perform logical deductions, mathematical calculations, and scientific analysis.
Multilingual Understanding: I understand and generate text in multiple languages, including English, Chinese, and others.

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L5N5444-1🕒	0.86	“ justification”“ reason”“ reasoning”
2. L4N8276+1💥	0.86	“ consideration”“ reasoning”“ reason”
3. L17N7680-1🕒	0.85	“ assumption”“ justified”“ assumptions”
4. L10N5253-1🕒	0.84	“ reason”“ reasoning”“ reasoned”
5. L3N6076+1🕒	0.83	“ reasonable”“ reason”“ judgement”
6. L6N8163-1🕒	0.79	“ reason”“ reasons”“ justification”
7. L11N5102-1🕒	0.79	“ reasoning”“ justification”“ presenting”
8. L16N7711-1🕒	0.79	“ justification”“ reason”“理由”
9. L9N5949-1🕒	0.78	“ reason”“ reasons”“ justification”
10. Virtue Loop✅ L9N2721+1	0.75	“ reason”“ justification”“ justified”

Shadow specimen, apart from the ten: L11N8415+1💤, -0.06.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 11, neuron 8415, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.78, top-1 agreement 0.68) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L11N8415+1💤 shadow specimen t0-v0.1	0.775	0.68	1.017	1.18	“ ”“<\|im_end\|>”“ you”“ ”“ "”“ ____”“ **”“ _____”
L11N8415-1 t0-v0.1	0.780	0.68	0.990	1.20	Top boosted tokens ↑

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.